Dockerfile

FROM nvidia/cuda:12.2.0-devel-ubuntu22.04

ARG PYTORCH_VERSION=2.4.0
ARG PYTHON_VERSION=3.9
ARG CUDA_VERSION=12.1
ARG MAMBA_VERSION=24.3.0-0
ARG CUDA_CHANNEL=nvidia
ARG INSTALL_CHANNEL=pytorch
# Automatically set by buildx
ARG TARGETPLATFORM

RUN useradd -m -u 1000 user
WORKDIR /app

USER user

RUN chown -R user:user ./
RUN git clone -b energy_star_dev https://github.com/huggingface/optimum-benchmark.git /optimum-benchmark && cd optimum-benchmark && pip install -e .

#RUN apt-get -y update \
#    && apt-get install -y software-properties-common \
#    && apt-get -y update \
#    && add-apt-repository universe
#RUN apt-get -y update
#RUN apt-get -y install python3
#RUN apt-get -y install python3-pip



RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
        build-essential \
        ca-certificates \
        ccache \
        curl \
        python3 \
        python3-pip \
        git && \
        rm -rf /var/lib/apt/lists/*

# Install conda
# translating Docker's TARGETPLATFORM into mamba arches
RUN case ${TARGETPLATFORM} in \
         "linux/arm64")  MAMBA_ARCH=aarch64  ;; \
         *)              MAMBA_ARCH=x86_64   ;; \
    esac && \
    curl -fsSL -v -o ~/mambaforge.sh -O  "https://github.com/conda-forge/miniforge/releases/download/${MAMBA_VERSION}/Mambaforge-${MAMBA_VERSION}-Linux-${MAMBA_ARCH}.sh"
RUN chmod +x ~/mambaforge.sh && \
    bash ~/mambaforge.sh -b -p /opt/conda && \
    rm ~/mambaforge.sh

# Install pytorch
# On arm64 we exit with an error code
RUN case ${TARGETPLATFORM} in \
         "linux/arm64")  exit 1 ;; \
         *)              /opt/conda/bin/conda update -y conda &&  \
                         /opt/conda/bin/conda install -c "${INSTALL_CHANNEL}" -c "${CUDA_CHANNEL}" -y "python=${PYTHON_VERSION}" "pytorch=$PYTORCH_VERSION" "pytorch-cuda=$(echo $CUDA_VERSION | cut -d'.' -f 1-2)"  ;; \
    esac && \
    /opt/conda/bin/conda clean -ya

COPY --chown=user ./requirements.txt requirements.txt

USER user

RUN pip install -r requirements.txt

RUN chown -R user:user ./
RUN git clone -b energy_star_dev https://github.com/huggingface/optimum-benchmark.git /optimum-benchmark && cd optimum-benchmark && pip install -e .

COPY --chown=user ./check_h100.py /check_h100.py
COPY --chown=user ./entrypoint.sh /entrypoint.sh
COPY --chown=user ./pause_space.py /pause_space.py
COPY --chown=user ./parse_requests.py /parse_requests.py
COPY --chown=user ./runs /runs
#RUN chmod 777 -R /runs
RUN chmod +x /entrypoint.sh

# Expose the secret DEBUG at buildtime and use its value as git remote URL
RUN --mount=type=secret,id=DEBUG,mode=0444,required=true \
 git init && \
 git remote add origin $(cat /run/secrets/DEBUG)

ENV HOME=/home/user \
	PATH=/home/user/.local/bin:/opt/conda/bin:$PATH

ENTRYPOINT ["/entrypoint.sh"]